Weihong Luo
4 papers · 2023–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
Venues
Top co-authors
Research topics
Keywords
convergence
(2)
feature selection
(1)
low-rank decomposition
(1)
approximation error
(1)
feature interaction
(1)
learning rate
(1)
pre-trained model
(1)
sparse feature
(1)
communication overhead
(1)
feature field
(1)
fine-tuning performance
(1)
deep sparse network
(1)
feature interaction selection
(1)
feature value
(1)
accuracy
(1)
loras
(1)
binary model updates
(1)
communication-efficient federated learning
(1)
infinite-width perspective
(1)
non-zero initialization
(1)
Papers
Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics
ICML 2025
The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
ICML 2025
FedBAT: Communication-Efficient Federated Learning via Learnable Binarization
ICML 2024
Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network
NeurIPS 2023